Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    reproduction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    0.62
    us
    0.61
    (
    0.59
     a
    0.51
    .”
    0.51
    Identify
    0.49
    rol
    0.48
    وم
    0.48
     augment
    0.48
    ust
    0.47
    POSITIVE LOGITS
     reproduced
    0.64
     вам
    0.54
     बड़े
    0.51
     bạn
    0.51
     giản
    0.50
     दक्षिणी
    0.49
     любой
    0.48
     нему
    0.48
     പൂര്‍
    0.47
    ര്‍ക്കും
    0.47
    Act Density 0.000%

    No Known Activations